NCS and MS-based similar object real-time detection method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for real-time detection of objects, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as high cost and achieve high real-time effects
Active Publication Date: 2020-09-11
GUIZHOU POWER GRID CO LTD
View PDF12 Cites 5 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0002] At present, in the field of image detection, object detection technologies based on image workstations or network services, magnetic field sensors, and neural computing sticks have been very mature, but in some specific industrial production scenarios, it is necessary for the Objects are detected in real time, and the specific corresponding numbered objects of the objects are identified, and their process data is stored, which cannot be satisfied by the traditional single-camera object detection technology.
[0003] Traditional multi-object real-time detection needs to correspond to multiple cameras, and use the network to transmit data in real time to an image workstation with a high-end GPU for real-time detection, which is extremely expensive for large-scale industrial applications
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0034] Object detection is a core research issue of computer vision, and it has been widely used in the fields of visual environment perception, intelligent video analysis, image detection, etc. Influencing factors such as rigid deformation, local occlusion, and complex backgrounds cause large changes in the appearance characteristics of objects, which bring great challenges and uncertainties to object detection algorithms.
[0035] refer to figure 1 , figure 2 and image 3 , which is the first embodiment of the present invention, this embodiment provides a real-time detection method for similar objects based on NCS and MS, including:
[0036] S1: Collect image data of similar objects for preprocessing, extract edge feature parameters to construct a sample data set. It should be noted that preprocessing image data includes:
[0037] Eliminate the noise points of the image data, set the detection value, and sequentially detect the pixels in the image data;
[0038] Compar...
Embodiment 2
[0102] refer to Figure 4 , which is the second embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a real-time detection system for similar objects based on NCS and MS, including:
[0103] The collection module 100 is used to collect image data of similar objects, which includes a camera 101 and a magnetic field sensor 102. The camera 101 is used to detect and shoot pictures of similar objects in real time, and the magnetic field sensor 102 is used to capture the rotation angle of the data collected by the camera 101 in real time.
[0104] The image sensing module 200 is connected with the camera 101 , and is used to acquire the photographed pictures of similar objects, perform feature processing on them, recognize them, convert them into image data, and transmit them to the core processing module 300 .
[0105] The core processing module 300 is used to uniformly calculate and process the image data and the rotation ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses an NCS and MS-based similar object real-time detection method and system, and the method comprises: collecting the image data of a similar object, carrying out the preprocessing, extracting edge feature parameters, and constructing a sample data set; inputting the sample data set into a recognition model for training, ending the training until a training precision thresholdis met, and outputting a recognition result; performing detection classification of corresponding object numbers on the identification result by using a decision model, advancing a detection processin real time in combination with an AI accelerator, and outputting a corresponding detection result; and importing the detection result into a Bayesian analysis model to carry out secondary verification judgment, and displaying the verification result and the detection result in real time by using a mobile terminal or a Raspberry Pi display. According to the method, the image detection object canbe rapidly propelled and the specific object of the object can be identified so that the problem that the specific object cannot be judged in the process of image detection of multiple similar objectscan be solved, and the method has relatively high real-time performance, accuracy, applicability and economy.
Description
technical field [0001] The invention relates to the technical field of image detection, in particular to a method and system for real-time detection of similar objects based on NCS and MS. Background technique [0002] At present, in the field of image detection, object detection technologies based on image workstations or network services, magnetic field sensors, and neural computing sticks have been very mature, but in some specific industrial production scenarios, it is necessary for the The object is detected in real time, and the specific corresponding numbered object of the object is identified, and its process data is stored, which cannot be satisfied by the traditional single-camera object detection technology. [0003] Traditional multi-object real-time detection needs to correspond to multiple cameras, and use the network to transmit data in real time to an image workstation with a high-end GPU for real-time detection, which is extremely expensive for large-scale i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more